Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.3286. Min Act: -0.1700
Data Index: 1592720 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.2661. Min Act: -0.1700
Data Index: 2904688 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.2036. Min Act: -0.1700
Data Index: 372109 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.2036. Min Act: -0.1700
Data Index: 8519771 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.1724. Min Act: -0.1700
Data Index: 6800585 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.1724. Min Act: -0.1700
Data Index: 5411470 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.1411. Min Act: -0.1700
Data Index: 5287108 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.1099. Min Act: -0.1700
Data Index: 154521 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0786. Min Act: -0.1700
Data Index: 792996 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0474. Min Act: -0.1700
Data Index: 659560 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4948939 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0474. Min Act: -0.1700
Data Index: 4313362 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0474. Min Act: -0.1700
Data Index: 5049360 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0161. Min Act: -0.1700
Data Index: 2613926 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0161. Min Act: -0.1700
Data Index: 510060 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3286. Min Range: -6.3286
Max Act: 6.0161. Min Act: -0.1700
Data Index: 3790075 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3286. Min Range: -6.3286
Max Act: 5.9849. Min Act: -0.1700
Data Index: 7165509 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3286. Min Range: -6.3286
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1856443 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3286. Min Range: -6.3286
Max Act: 5.9536. Min Act: -0.1700
Data Index: 1011168 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3286. Min Range: -6.3286
Max Act: 5.9536. Min Act: -0.1700
Data Index: 160732 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19